Laguna XS 2.1 (Reasoning) vs GPT-6.1 Sol (medium)
Results updated 8 November 2026 · In Terminus-2 and Codex, so part of any gap can come from the harness · How we benchmark
Verdict
GPT-6.1 Sol (medium) clearly beats Laguna XS 2.1 (Reasoning) by 45 points, and is cheaper and faster.
- Cost per task
- $0.054 vs $0.046
- Time per task
- 17.3 min vs 0.4 min
- Tokens per attempt
- 937k vs 89k
- Image input
- No vs Yes
GPT-6.1 Sol (medium), Codex scores higher than Laguna XS 2.1 (Reasoning), Terminus-2 on all 3 evaluations scored for both. GPT-6.1 Sol (medium), Codex is cheaper and faster: $0.046 against $0.054 per task, and 0.4 min against 17.3 min.
Where they differ most
By kind of work, share of tasks passed, 0 to 100 · Higher is better
| Kind of work | Laguna XS 2.1 (Reasoning) | GPT-6.1 Sol (medium) |
|---|---|---|
| GIS analysis | 35 | 94 |
| Remote sensing and raster analysis | 39 | 85 |
| Climate and time series | 36 | 76 |
| Making maps | 53 | 81 |
Where the tasks are set: each kind of work links to its tasks and scoresCharts for each: Laguna XS 2.1 (Reasoning), Terminus-2 · GPT-6.1 Sol (medium), Codex.
Side by side
| Metric | Laguna XS 2.1 (Reasoning), Terminus-2 | GPT-6.1 Sol (medium), Codex |
|---|---|---|
| Geospatial Agent Index: Text only | 37 | 82 |
| Geospatial Agent Index: Text + vision | No data | No data |
| Earth-Bench V2 score | 44 | 72 |
| GeoBenchX score | 33 | 79 |
| GS-QA2 score | 35 | 93 |
| Vision agents score | No data | No data |
| GeoAgentBench score (Guided workflows; not in the Agent Index) | 63 | 100 |
| GeoAnalystBench score (Guided workflows; not in the Agent Index) | 63 | 100 |
| OGD4All score (standalone; in no index) | 65 | No data |
| GeoNatureAgent score (standalone; in no index) | 36 | No data |
| MultiGlobeQA score (standalone; in no index) | 59 | No data |
| GeoAgentEval score (standalone; in no index) | 60 | No data |
| ImpactMesh score (standalone; in no index) | No data | No data |
| Remote sensing and raster analysis score | 39 | 85 |
| Change detection score | 48 | 68 |
| GIS analysis score | 35 | 94 |
| Climate and time series score | 36 | 76 |
| Making maps score | 53 | 81 |
| Cost per task | $0.054 | $0.046 |
| Time per task (at 100 output tokens/s) | 17.3 min | 0.4 min |
| Tokens per attempt | 937k | 89k |
| Turns per attempt | 36.7 | 5.8 |
| Input price per 1M tokens | $0.10 | $2.00 |
| Output price per 1M tokens | $0.20 | $10.00 |
| Context window | 262,144 | 1,050,000 |
| Image input | No | Yes |
| Developer | Poolside | OpenAI |
Frequently asked questions
Which scores higher on the Geospatial Agent Index, Laguna XS 2.1 (Reasoning), Terminus-2 or GPT-6.1 Sol (medium), Codex?
GPT-6.1 Sol (medium), Codex, 82 to 37.
Which is cheaper per task, Laguna XS 2.1 (Reasoning), Terminus-2 or GPT-6.1 Sol (medium), Codex?
GPT-6.1 Sol (medium), Codex, $0.046 to $0.054.
Which writes fewer output tokens per task, Laguna XS 2.1 (Reasoning), Terminus-2 or GPT-6.1 Sol (medium), Codex?
GPT-6.1 Sol (medium), Codex, 1k to 24k.
Which has the larger context window, Laguna XS 2.1 (Reasoning), Terminus-2 or GPT-6.1 Sol (medium), Codex?
GPT-6.1 Sol (medium), Codex, 1,050,000 tokens to 262,144 tokens.